Method, computer device, and program for curating content through chatbot

Abstract

To provide a method, a computer device, and a program for curating a content on various topics through a chatbot.SOLUTION: A content curation method includes the steps of: generating a recommended content for at least one topic using an original content produced on at least one platform; providing the recommended content to a user using a chatbot for content curation; collecting a user feedback as a user response to the recommended content through interaction with the chatbot; and reflecting the user response in at least personalization recommendation to the user or a report related to the recommended content.SELECTED DRAWING: Figure 3

Description

[Technical Field]

[0001] The present disclosure relates to a technique for providing recommended content. [Background technology]

[0002] Social media, such as social networking services (SNS) and messengers, is a general term for services that strengthen relationships between people, building connections between users and supporting interactions through posts.

[0003] Social media provides information to users in different contexts, for example, social media provides updates on user connections, updates on posts, content recommendations, and many other information items.

[0004] For example, Patent Document 1 (registered June 29, 2017) discloses a technology for managing posts using SNS.

[0005] In addition, as the use of social media becomes more widespread and the functions provided through such platforms become increasingly diverse, video platform services are being offered that allow for the distribution and sharing of short-form content, which is short videos of approximately 15 seconds to 10 minutes in length. [Prior art documents] [Patent documents]

[0006] [Patent Document 1] Korean Patent Registration No. 10-1754373 Summary of the Invention [Problem to be solved by the invention]

[0007] Using generative AI (artificial intelligence), we can provide a content curation service that categorizes and summarizes the latest content produced on various platforms by topic and recommends it to users.

[0008] For users who have added a content curation chatbot as a friend, the chatbot can randomly select topics and recommend summary content for the selected topics.

[0009] Through dialogue with users who have read the recommended content, the user's reaction to the content can be collected and reflected in the next recommendation.

[0010] By including information about the creator in the content recommendation, rewards and reports can be provided to the creator depending on the user's response. [Means for solving the problem]

[0011] According to the present disclosure, there is provided a content curation method for a computer device including at least one processor, the content curation method including: a step of generating, by the at least one processor, recommended content related to at least one topic using original content produced on at least one platform; a step of providing, by the at least one processor, the recommended content to a user using a chatbot for content curation; a step of collecting, by the at least one processor, user feedback as the user's reaction to the recommended content through interaction with the chatbot; and a step of reflecting, by the at least one processor, the user's reaction in at least one of a personalized recommendation to the user and a report on the recommended content.

[0012] According to one aspect, the step of generating recommended content may include classifying the original content by topic and generating recommended content for each topic.

[0013] According to another aspect, generating the recommended content may include categorizing the original content by topic and using generative AI to generate the recommended content by summarizing the content categorized by topic.

[0014] According to another aspect, the step of generating the recommended content may generate the recommended content using original content created on the platform within a recent certain period of time.

[0015] According to another aspect, providing the recommended content may include providing reference information indicating original content from which the recommended content originates.

[0016] According to another aspect, the reference information may include at least one of a link to the original content and information about the creator.

[0017] According to another aspect, the step of providing the recommended content may include providing the user with recommended content for a topic randomly selected from recommended content for each topic.

[0018] According to another aspect, the step of collecting user feedback may include, when it is determined that the user has read the recommended content, collecting the user's reaction to the recommended content through a dialogue between the chatbot and the user after a certain period of time has elapsed from that point.

[0019] According to yet another aspect, the reflecting step may include extracting user personalized information for recommending content based on the user's response.

[0020] According to another aspect, the user personalized information may include at least one of a preference level and a registration status for each topic.

[0021] According to another aspect, the reflecting step may include providing an effect report based on users who have flowed in through the recommended content to a creator of the original content from which the recommended content originates.

[0022] According to another aspect, the reflecting step may include providing the creator of the original content with a statistical report summarizing user responses to the recommended content by topic.

[0023] According to another aspect, the statistical report may include a summary of positive and negative interactions between the user and the recommended content.

[0024] According to yet another aspect, the content curation method further includes a step of sharing, by at least one processor, user reactions in an open chat related to the recommended content, and the step of sharing the user reactions may include, if the recommended content is generated based on the most recent conversation in the open chat, summarizing the conversation with the user regarding the content and sharing it in the open chat.

[0025] According to the present disclosure, there is provided a computer program recorded on a computer-readable recording medium for causing a computer device to execute a content curation method. Also, according to the present disclosure, there is provided a program for causing a computer device to execute a content curation method.

[0026] According to the present disclosure, there is provided a computer device including at least one processor configured to execute computer device-readable instructions, wherein the at least one processor generates recommended content related to at least one topic using original content produced on at least one platform, provides the recommended content to a user using a chatbot for content curation, collects user feedback as the user's reaction to the recommended content through interaction with the chatbot, and reflects the user's reaction in at least one of a personalized recommendation to the user and a report on the recommended content. [Effects of the Invention]

[0027] Using generative AI (artificial intelligence), we can provide a content curation service that categorizes and summarizes the latest content produced on various platforms by topic and recommends it to users. [Brief explanation of the drawings]

[0028] [Figure 1] FIG. 1 is a diagram illustrating an example of a network environment according to an embodiment of the present disclosure. [Figure 2] FIG. 1 is a block diagram illustrating an example of a computer device according to an embodiment of the present disclosure. [Figure 3] 1 is a flowchart illustrating an example of a method that can be performed by a computer device in one embodiment of the present disclosure. [Figure 4] FIG. 2 is a diagram illustrating an example of original content of a topic according to an embodiment of the present disclosure. [Figure 5] FIG. 10 is a diagram illustrating another example of original content of a topic according to an embodiment of the present disclosure. [Figure 6] FIG. 10 is a diagram illustrating yet another example of original content of a certain topic according to an embodiment of the present disclosure. [Figure 7] FIG. 10 is a diagram illustrating an example of a result of summarizing original content of a certain topic in one embodiment of the present disclosure. [Figure 8] FIG. 10 is a diagram illustrating an example of recommended content created based on a summary of content in one embodiment of the present disclosure. [Figure 9] FIG. 10 is a diagram illustrating an example of delivery of recommended content according to an embodiment of the present disclosure. [Figure 10] FIG. 10 is a diagram illustrating an example of user interaction regarding recommended content in one embodiment of the present disclosure. [Figure 11] FIG. 10 is a diagram showing another example of user interaction regarding recommended content according to an embodiment of the present disclosure. [Figure 12] FIG. 10 is a diagram showing an example of user personalized information in one embodiment of the present disclosure. [Figure 13] FIG. 10 illustrates an example of a statistical report regarding recommended content according to an embodiment of the present disclosure. DETAILED DESCRIPTION OF THE INVENTION

[0029] Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings.

[0030] FIELD Embodiments of the present invention relate to a technique for providing recommended content.

[0031] Embodiments including those specifically disclosed in this specification can eliminate bias in content consumption and provide an environment where content on a wider variety of topics can be accessed by classifying and summarizing content produced on multiple platforms by topic, and then recommending summary content on randomly selected topics through a chatbot.

[0032] A content curation system according to an embodiment of the present invention may be realized by at least one computer device, and a content curation method according to an embodiment of the present invention may be executed by at least one computer device included in the content curation system. In this case, a computer program according to an embodiment of the present invention may be installed and executed in the computer device, and the computer device may execute the content curation method according to an embodiment of the present invention under the control of the executed computer program. The computer program may be recorded on a computer-readable recording medium so as to be combined with the computer device and cause the computer to execute the content curation method.

[0033] FIG. 1 is a diagram showing an example of a network environment in one embodiment of the present invention. The network environment in FIG. 1 shows an example including multiple electronic devices 110, 120, 130, and 140, multiple servers 150 and 160, and a network 170. FIG. 1 is merely an example for explaining the invention, and the number of electronic devices and the number of servers are not limited to those shown in FIG. 1. Furthermore, the network environment in FIG. 1 is merely an example of an environment applicable to this embodiment, and environments applicable to this embodiment are not limited to the network environment in FIG. 1.

[0034] The electronic devices 110, 120, 130, and 140 may be fixed or mobile terminals implemented by computers. Examples of the electronic devices 110, 120, 130, and 140 include smartphones, mobile phones, navigation systems, personal computers (PCs), notebook PCs, digital broadcasting terminals, personal digital assistants (PDAs), portable multimedia players (PMPs), and tablets. While FIG. 1 illustrates a smartphone as an example of the electronic device 110, in embodiments of the present invention, the electronic device 110 may represent one of a variety of physical computer devices capable of communicating with the other electronic devices 120, 130, and 140 and / or the servers 150 and 160 via the network 170 using a substantially wireless or wired communication method.

[0035] The communication method is not limited, and may include not only communication methods using communication networks (for example, a mobile communication network, a wired Internet, a wireless Internet, and a broadcast network) that can be included in network 170, but also short-range wireless communication between devices. For example, network 170 may include any one or more of networks such as a personal area network (PAN), a local area network (LAN), a campus area network (CAN), a metropolitan area network (MAN), a wide area network (WAN), a broadband network (BBN), and the Internet. Furthermore, network 170 may include any one or more of network topologies including, but not limited to, a bus network, a star network, a ring network, a mesh network, a star-bus network, a tree or hierarchical network, etc.

[0036] Each of the servers 150, 160 may be implemented by one or more computing devices that communicate with the plurality of electronic devices 110, 120, 130, 140 via the network 170 to provide instructions, code, files, content, services, etc. For example, the server 150 may be a system that provides a service (such as a content curation service, for example) to the plurality of electronic devices 110, 120, 130, 140 connected via the network 170.

[0037] 2 is a block diagram showing an example of a computer device according to an embodiment of the present invention. Each of the electronic devices 110, 120, 130, and 140 and each of the servers 150 and 160 described above may be realized by a computer device 200 shown in FIG.

[0038] As shown in FIG. 2 , such a computer device 200 may include a memory 210, a processor 220, a communication interface 230, and an input / output interface 240. The memory 210 is a computer-readable recording medium and may include random access memory (RAM), read-only memory (ROM), and a persistent mass storage device such as a disk drive. Here, a persistent mass storage device such as a ROM or a disk drive may be included in the computer device 200 as a separate persistent storage device distinct from the memory 210. The memory 210 may also store an operating system and at least one program code. Such software components may be loaded into the memory 210 from a computer-readable recording medium separate from the memory 210. Such separate computer-readable recording medium may include a computer-readable recording medium such as a floppy drive, a disk, a tape, a DVD / CD-ROM drive, or a memory card. In another embodiment, the software components may be loaded into the memory 210 through a communication interface 230, which is not a computer-readable recording medium. For example, the software components may be loaded into the memory 210 of the computer device 200 based on a computer program installed by a file received over the network 170 .

[0039] Processor 220 may be configured to process computer program instructions by performing basic arithmetic, logic, and input / output operations. The instructions may be provided to processor 220 by memory 210 or by communication interface 230. For example, processor 220 may be configured to execute instructions received according to program code stored in a storage device such as memory 210.

[0040] The communication interface 230 may provide a function for the computer device 200 to communicate with other devices (e.g., the above-mentioned storage device) via the network 170. For example, requests, instructions, data, files, etc. generated by the processor 220 of the computer device 200 in accordance with program code stored in a storage device such as the memory 210 may be transmitted to other devices via the network 170 under the control of the communication interface 230. Conversely, signals, instructions, data, files, etc. from other devices may be received by the computer device 200 via the communication interface 230 of the computer device 200 via the network 170. The signals, instructions, data, etc. received via the communication interface 230 may be transmitted to the processor 220 or the memory 210, and files, etc. may be recorded on a storage medium (e.g., the above-mentioned permanent storage device) that the computer device 200 may further include.

[0041] The input / output interface 240 may be a means for interfacing with the input / output device 250. For example, the input device may include a device such as a microphone, keyboard, or mouse, and the output device may include a device such as a display or speaker. As another example, the input / output interface 240 may be a means for interfacing with a device that integrates input and output functions into one, such as a touch screen. The input / output device 250 may be configured as a single device together with the computer device 200.

[0042] Also, in other embodiments, computing device 200 may include fewer or more components than those shown in Figure 2. However, most prior art components need not be explicitly shown. For example, computing device 200 may be configured to include at least some of the input / output devices 250 described above, and may further include other components such as a transceiver, a database, etc.

[0043] Specific embodiments of a method and apparatus for curating content on various topics through a chatbot are described below.

[0044] The computer device 200 according to the present embodiment may provide a content curation service to a client through a dedicated application installed on the client or through connection to a web / mobile site associated with the computer device 200. A content curation system implemented by a computer may be configured in the computer device 200. For example, the content curation system may be implemented as an independently operating program, or may be configured as an in-app for a specific application and be operable on the specific application.

[0045] The processor 220 of the computing device 200 may be implemented with components for performing the following content curation methods. Depending on the embodiment, the components of the processor 220 may be selectively included or excluded from the processor 220. Also, depending on the embodiment, the components of the processor 220 may be separated or combined to express the functionality of the processor 220.

[0046] Such processor 220 and components of processor 220 may control computing device 200 to perform steps included in the following content curation method, for example, processor 220 and components of processor 220 may be configured to execute instructions from operating system code and at least one program code contained in memory 210.

[0047] Here, the components of the processor 220 may represent different functions that are performed by the processor 220 according to instructions provided by program code stored on the computer device 200 .

[0048] The processor 220 may read the necessary instructions from the memory 210, which is loaded with instructions related to the control of the computing device 200. In this case, the read instructions may include instructions for controlling the processor 220 to perform the steps described below.

[0049] The steps included in the content curation method described below may be performed in a different order than that shown in the figures, and some steps may be omitted or additional processes may be included.

[0050] The steps involved in the content curation method may be performed on the server 150, although in some embodiments at least some of the steps may be performed on the client.

[0051] FIG. 3 is a flowchart illustrating an example method that may be performed by a computing device in accordance with an embodiment of the present invention.

[0052] Referring to FIG. 3, in step 310, the processor 220 may classify and summarize content generated by at least one platform (hereinafter referred to as "original content") by topic and generate content to be recommended (hereinafter referred to as "recommended content") for each topic. The processor 220 may create the recommended content for each topic using original content publicly posted on a social media platform or another platform linked to social media. In this specification, "social media" may refer to social networking services such as messengers and various communities, as well as integrated media platforms that provide various services utilizing resources such as user profile information and friendships within social networking services. For example, the processor 220 may integrate content generated over a recent period (e.g., 24 hours) from multiple platforms implemented on the server 150, such as a video service, an open chat function of a messenger, and a news service, and classify and summarize the content by topic. In this case, the processor 220 may classify original content most recently provided on multiple platforms by topic using at least one of published document classification technologies. The processor 220 may then summarize the most recent content categorized by topic using a generative AI such as a chat GPT (generative pre-trained transformer), and generate recommended content based on the summary. In this case, the processor 220 may record reference information indicating the original content used to summarize or generate the content, i.e., the source of the content, in association with the recommended content. The reference information may include a link to the original content and information about the creator of the content.

[0053] In step 320, the processor 220 may provide recommended content to a user who has added a dedicated chatbot for content curation (hereinafter referred to as a "curator bot") as a friend. For example, the processor 220 may provide the user with recommended content for a selected topic from recommended content generated for each topic using various approaches, such as a report method or a dialogue using the curator bot. The processor 220 may randomly select topics to approach various topics and provide the recommended content for the selected topic. In some embodiments, the processor 220 may also provide recommended content for a topic selected based on the user's preference. In providing the recommended content, the processor 220 may also provide information about the original content from which the recommended content is derived, i.e., reference information including creator information of the original content.

[0054] In step 330, the processor 220 may collect a user's reaction to the recommended content. The processor 220 may use a curator bot to interact with the user and collect the user's reaction to the recommended content through the interaction between the curator bot and the user. For example, the processor 220 may attempt to have a dialogue with the user a certain time after providing the user with the recommended content, and collect user feedback such as an evaluation of the recommended content itself or the topic of the recommended content through questions and answers related to the recommended content, a survey, or confirmation of intention to register. Here, intention to register may be, for example, an intention to add the content, topic, etc. to a recommendation list or a favorites list.

[0055] In step 340, the processor 220 may extract personalized information for the user based on the user's response and reflect it in the next recommendation. In order to recommend content to the user, the processor 220 may understand personalized information such as the preference, interest, and registration status for the recommended content itself or the topic of the recommended content from the interaction data between the curator bot and the user.

[0056] In step 350, the processor 220 may provide a report related to the recommended content based on the user's response. As one example, the processor 220 may provide the creator of the original content from which the recommended content originates with an effect report such as an increase or decrease in the number of content views or follows by users who have accessed the recommended content. As another example, the processor 220 may provide, upon request from the creator, a statistical report aggregating user responses to the recommended content by topic to help the creator with content creation.

[0057] 4 to 6 are diagrams showing examples of original content of a certain topic in one embodiment of the present invention.

[0058] Figures 4-6 show examples of original content categorized under the topic "environmental protection."

[0059] Referring to FIG. 4, the processor 220 may perform topic classification based on the content of the body 410 of posts 400 set to public view among posts created by users within the past day on a platform where users share posts in various formats, such as text, images, and videos. The content classification may include text, images, videos, and the like that may be included in the body 410. Reactions of users who read the posts 400, such as comments 420, may also be used to summarize the content of the topic to which the posts 400 belong. Reference information, including links to the posts 400, which are the original data used to summarize the content for each topic, and author information, may be recorded and used for future follow-up guidance, notifications, and the like.

[0060] 5, the processor 220 may classify topics based on the title 510 and conversation content 520 of the chat room 500, which is operated as a public chat on Messenger. Because the interests of the public chat may change over time, the conversation content 520 exchanged during a predetermined period may be summarized. In the case of a public chat, only the anonymous conversation content 520 may be summarized, and a link to the open chat room 500 used for summarizing the content by topic may be recorded as reference information.

[0061] 6, the processor 220 may categorize topics based on the title 610 and body 620 of news 600 posted on the news platform in the past day. In the case of news 600, text, images, videos, etc. that may be included in the body 620 may be included in the content categorization, and user reactions after reading the news 600, such as comments 630, may also be used to summarize the content of the topic to which the news 600 belongs. Reference information including a link to the news 600, which is the original data used to summarize the content for each topic, and creator information may be recorded.

[0062] The results of summarizing the original content in Figures 4 to 6, i.e., posts 400, open chat rooms 500, and news 600 categorized under the topic of "environmental protection," are shown in Figure 7, and the content summary 700 may consist of a title 710 and a description 720 for each original content.

[0063] FIG. 8 is a diagram showing an example of recommended content created based on a content summary in one embodiment of the present invention.

[0064] The processor 220 may generate recommended content for each topic based on summaries of original content categorized by topic. For example, for the topic "environmental protection," the processor 220 may summarize original content generated over the past day on various platforms, such as video services, open chats on messengers, and news services, and then use the summary to create a post 800 on the topic "environmental protection" as shown in FIG. 8. The recommended content may be generated in the form of a post 800 to be displayed on a video service platform. Each post 800 created as recommended content may include text, images, videos, and other content extracted from the original content, as well as text, images, videos, and other content generated by a generative AI based on the summary. Furthermore, the creation of the post 800 may include reference information 810, including a link to the original content from which the post 800 originates, creator information, and the like.

[0065] FIG. 9 is a diagram showing an example of distribution of recommended content in one embodiment of the present invention.

[0066] The processor 220 may provide recommended content for a randomly selected topic from the recommended content for each topic to a user who has added the curator bot as a friend on Messenger, through a chat room in which the curator bot and the user participate. Referring to FIG. 9, the processor 220 may publish a guide message 901 for the recommended content for the randomly selected topic in the form of a conversation message with the curator bot through a chat room 900 with the curator bot. The guide message 901 may include a link for checking the recommended content. For example, the guide message 901 may include a link to a post 800 created as the recommended content and a brief description of the topic of the post 800. When the user selects the link included in the guide message 901, the user may be taken to a service screen in which the post 800 shown in FIG. 8 is displayed.

[0067] 10 and 11 are diagrams showing examples of user interactions regarding recommended content in one embodiment of the present invention.

[0068] When the user reads the recommended content provided through the curator bot, for example, when the user selects a link included in the guidance message 901, the processor 220 may determine that the user has read the recommended content, and after a certain time has passed from that point, may attempt to interact with the user to collect the user's reaction to the recommended content. Referring to Fig. 10, when the user reads the recommended content, the processor 220 may collect user feedback such as an evaluation of the recommended content, a survey, and confirmation of intention to register through a chat room 900 with the curator bot.

[0069] 11, if the user does not read the recommended content provided through the curator bot, the processor 220 may collect feedback on topics the user likes through the chat room 900 with the curator bot. For example, the processor 220 may provide the remaining topics, excluding those for which the recommended content has been generated but not read by the user, as options so that the user can select a topic that is likely to interest them. If there is recommended content that has been delivered but not read, the processor 220 may prompt the user to read it through a reminder, and the response and reason may be checked and reflected in the next recommendation.

[0070] FIG. 12 is a diagram showing an example of user personalized information in one embodiment of the present invention.

[0071] The processor 220 may collect user responses to recommended content through a dialogue between the curator bot and the user and extract personalized information for the user based on the collected responses. Referring to FIG. 12, the processor 220 may collect user responses to recommended content and construct personalized information 1200, such as the user's rate of receiving recommended content for each topic, the preference level for each topic, and the user's registration status. The processor 220 may reflect the user's personalized information 1200 in the next recommendation. For example, recommendations may be provided focusing on topics for which the user has registered or preferred through a dialogue with the curator bot, and topics for which the user has unsubscribed may be excluded from the recommendations. Content for topics to be recommended may be provided based on the user's registration settings and preference level through a dialogue with the curator bot, or content for various topics may be provided through random recommendations for a certain percentage of a certain period of time, regardless of the user's registration settings and preference level. In addition to the preference level and registration status, the user may be able to specify the time and number of times to receive recommended content through a dialogue with the curator bot, and the recommended content may be distributed according to user-specified conditions.

[0072] The processor 220 may provide additional functions such as summarizing the content of a conversation between the user and the curator bot regarding the recommended content, and then reflecting the summary in the recommended content or sharing it in a chat room of a public chat. For example, in the case of recommended content generated in a recent conversation in a public chat, the content of the conversation between the curator bot and the user regarding the content may be summarized and shared in the public chat.

[0073] The processor 220 may provide a reward to the creator of the original content associated with the recommended content, including reference information from the source of the content, when recommending the content. The processor 220 may also provide an effect report, such as an increase or decrease in the number of content views or followers by users who have visited the recommended content, to the creator of the original content from which the recommended content originates, by a method such as notification.

[0074] The processor 220 may provide a statistical report that aggregates user responses to the recommended content for each topic to help creators create content. For example, as shown in FIG. 13 , a statistical report 1300 of recommended content for each topic may include information on the number of times the recommended content has been distributed, information on the increase or decrease in the number of followers of users who have come through the recommended content, information on the number of times the recommended content has been read, and positive and negative responses to the recommended content. Through interaction with the curator bot, the content of the exchange between the user and the recommended content regarding the recommended content may be classified into positive and negative content through sentiment analysis, and the positive and negative content may be summarized and included in the statistical report 1300.

[0075] As such, according to an embodiment of the present invention, content curation is provided that uses generative AI to classify, summarize, and recommend the latest content created on various platforms by topic, thereby improving users' content consumption experience, revitalizing communities by strengthening connections between creators and users, and increasing service revenue through targeting based on personalized information obtained from user responses.

[0076] The above-described devices may be realized using hardware components, software components, and / or a combination of hardware and software components. For example, the devices and components described in the embodiments may be realized using one or more general-purpose or special-purpose computers, such as a processor, a controller, an arithmetic logic unit (ALU), a digital signal processor, a microcomputer, a field programmable gate array (FPGA), a programmable logic unit (PLU), a microprocessor, or various devices capable of executing and responding to instructions. The processing device may execute an operating system (OS) and one or more software applications running on the OS. The processing device may also access, record, manipulate, process, and generate data in response to the execution of the software. For ease of understanding, a single processing device may be described. However, those skilled in the art will understand that a processing device may include multiple processing elements and / or multiple types of processing elements. For example, a processing device may include multiple processors or one processor and one controller. Other processing configurations, such as parallel processors, are also possible.

[0077] Software may include computer programs, codes, instructions, or a combination of one or more of these, which may configure a processing device to operate as desired or may independently or collectively instruct the processing device. The software and / or data may be embodied in any type of machine, component, physical device, computer storage medium, or device to be interpreted by the processing device or to provide instructions or data to the processing device. The software may be distributed and stored and executed in a distributed manner on computer systems connected by a network. The software and data may be stored on one or more computer-readable storage media.

[0078] Methods according to embodiments may be implemented as program instructions executable by various computer means and recorded on a computer-readable medium. In this case, the medium may continuously record a computer-executable program or may temporarily record the program for execution or download. The medium may be various recording or storage means, including a single or multiple hardware components, and may be directly connected to a computer system or distributed across a network. Examples of media include magnetic media such as hard disks, floppy disks, and magnetic tapes; optical media such as CD-ROMs and DVDs; magneto-optical media such as floptical disks; and media configured to record program instructions, such as ROMs, RAMs, and flash memories. Other examples of media include recording media and storage media managed by app stores that distribute applications, websites that provide and distribute various software, and servers.

[0079] Although the embodiments have been described above based on limited examples and drawings, those skilled in the art will appreciate that various modifications and variations may be made from the above description. For example, the described techniques may be performed in an order different from that described, and / or the described system, structure, device, circuit, or other element may be coupled or combined in a manner different from that described, or may be substituted or replaced by other elements or equivalents, and still achieve suitable results.

[0080] Therefore, even if the embodiments differ from those described above, if they are equivalent to the scope of the claims, they fall within the scope of the appended claims.

[0081] This application claims priority based on Patent Application No. 10-2024-019718 filed with the Korean Intellectual Property Office on February 8, 2024, the entire contents of which are incorporated herein by reference. [Explanation of symbols]

[0082] 110, 120, 130, 140: Electronic equipment 150, 160: Server 170: Network

Claims

1. 1. A content curation method for a computer device including at least one processor, comprising: generating, by the at least one processor, recommended content related to at least one topic using original content produced on at least one platform; utilizing a chatbot for content curation to provide the recommended content to the user, by the at least one processor; collecting, by the at least one processor, user feedback as a user's reaction to the recommended content through interaction with the chatbot; and A content curation method comprising: reflecting, by the at least one processor, the user's response in at least one of a personalized recommendation to the user and a report on the recommended content.

2. The step of generating the recommended content includes: The content curation method according to claim 1 , wherein the original content is classified by topic, and recommended content related to each topic is generated.

3. The step of generating the recommended content includes: categorizing the original content by topic; and The content curation method of claim 1 , further comprising: generating the recommended content by summarizing content categorized by topic using generative AI.

4. The step of generating the recommended content includes: The content curation method according to claim 1 , wherein the recommended content is generated using the original content created on the platform within a recent certain period of time.

5. The step of providing the recommended content includes: The content curation method according to claim 1 , further comprising the step of providing reference information indicating an original content from which the recommended content originates.

6. The content curation method according to claim 5 , wherein the reference information includes at least one of a link to the original content and information about a creator.

7. The step of providing the recommended content includes: The content curation method according to claim 1, wherein recommended content for a topic selected randomly from recommended content for each topic is provided to the user.

8. The step of collecting user feedback includes: The content curation method described in claim 1, characterized in that when it is determined that a user has read the recommended content, after a certain period of time has passed from that point, the user's reaction to the recommended content is collected through a dialogue between the user and the chatbot.

9. The reflecting step includes: The content curation method according to claim 1 , further comprising extracting user personalized information for recommending content based on the user's response.

10. The content curation method according to claim 9 , wherein the user personalized information includes at least one of a preference level and a registration status for each topic.

11. The reflecting step includes: The content curation method according to claim 1 , further comprising the step of providing an effect report by users who have flowed in through the recommended content to a creator of the original content from which the recommended content originates.

12. The reflecting step includes: The content curation method according to claim 1 , further comprising providing a statistical report to the creator of the original content that compiles user responses to the recommended content for each topic.

13. The statistical report includes a summary of positive and negative interactions between the user and the recommended content. The content curation method according to claim 12, characterized in that:

14. and further comprising: sharing, by the at least one processor, the user's reaction in a public chat associated with the recommended content; The step of sharing the user's reaction includes: The content curation method described in claim 1, characterized in that if the recommended content is generated based on the most recent conversation in the open chat, the conversation between the user and the recommended content is summarized and shared in the open chat.

15. A program for causing the computer device to execute the content curation method according to any one of claims 1 to 14.

16. at least one processor configured to execute computer device readable instructions; The at least one processor generating recommended content relating to at least one topic using original content produced on at least one platform; utilizing a chatbot for content curation to provide the recommended content to the user; collecting user feedback as a user's reaction to the recommended content through interaction with the chatbot; A computer device characterized in that the user's reaction is reflected in at least one of a personalized recommendation to the user and a report on the recommended content.

17. The at least one processor The computer device of claim 16, wherein the original content is classified by topic, and then the recommended content is generated by summarizing the content classified by topic using a generative AI.

18. The at least one processor providing reference information indicating the original content from which the recommended content originates; 17. The computer device of claim 16, wherein the reference information includes at least one of a link to the original content and information about a creator.

19. The at least one processor extracts user personalization information for recommending content based on the user's response; and The computer device according to claim 16, wherein the user personalized information includes at least one of a preference level and a registration status for each topic.

20. The at least one processor The computer device of claim 16, characterized in that it provides the creator of the original content with at least one of an effect report from users who have come in through the recommended content and a statistical report that compiles user responses to the recommended content for each topic.

Images